Abstract

Retrieving videos of a specific person given his/her face image as query becomes more and more appealing for applications like smart movie fast-forwards and suspec-t searching. It also forms an interesting but challenging computer vision task, as the visual data to match, i.e., still image and video clip are usually represented quite different-ly. Typically, face image is represented as point (i.e., vector) in Euclidean space, while video clip is seemingly modeled as a point (e.g., covariance matrix) on some particular Rie-mannian manifold in the light of its recent promising suc-cess. It thus incurs a new hashing-based retrieval problem of matching two heterogeneous representations, respective-ly in Euclidean space and Riemannian manifold. This work makes the first attempt to embed the two heterogeneous s-paces into a common discriminant Hamming space. Specifi-cally, we propose Hashing across Euclidean space and Rie-mannian manifold (HER) by deriving a unified framework to firstly embed the two spaces into corresponding repro-ducing kernel Hilbert spaces, and then iteratively optimize the intra- and inter-space Hamming distances in a max-margin framework to learn the hash functions for the two spaces. Extensive experiments demonstrate the impressive superiority of our method over the state-of-the-art competi-tive hash learning methods. 1.